{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:20:03Z","timestamp":1778149203701,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.62072468"],"award-info":[{"award-number":["No.62072468"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Few-shot learning has achieved satisfactory progress over the years, but these methods implicitly hypothesize that the data in the base (source) classes and novel (target) classes are sampled from the same data distribution (domain), which is often invalid in reality. The purpose of cross-domain few-shot learning (CD-FSL) is to successfully identify novel target classes with a small quantity of labeled instances on the target domain under the circumstance of domain shift between the source domain and the target domain. However, in CD-FSL, the knowledge learned by the network on the source domain often suffers from the situation of inadaptation when it is transferred to the target domain, since the instances on the source and target domains do not obey the same data distribution. To surmount this problem, we propose a Target Oriented Dynamic Adaption (TODA) model, which uses a tiny amount of target data to orient the network to dynamically adjust and adapt during training. Specifically, this work proposes a domain-specific adapter to ameliorate the network inadaptability issues in transfer to the target domain. The domain-specific adapter can make the extracted features more specific to the tasks in the target domain and reduce the impact of tasks in the source domain by combining them with the mainstream backbone network. In addition, we propose an adaptive optimization method in the network optimization process, which assigns different weights according to the importance of different optimization tasks. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our TODA method.<\/jats:p>","DOI":"10.1007\/s11063-024-11508-0","type":"journal-article","created":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T10:01:22Z","timestamp":1714212082000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Target Oriented Dynamic Adaption for Cross-Domain Few-Shot Learning"],"prefix":"10.1007","volume":"56","author":[{"given":"Xinyi","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinjing","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"11508_CR1","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning, PMLR, pp 1126\u20131135"},{"key":"11508_CR2","unstructured":"Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems 30: annual conference on neural information processing systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp 4077\u20134087"},{"key":"11508_CR3","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, et\u00a0al (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"11508_CR4","unstructured":"Vinyals O, Blundell C, Lillicrap T, et\u00a0al (2016) Matching networks for one shot learning. In: Advances in neural information processing systems 29: annual conference on neural information processing systems 2016, December 5-10, 2016, Barcelona, Spain, pp 3630\u20133638"},{"key":"11508_CR5","doi-asserted-by":"publisher","unstructured":"Garcia V, Bruna J (2017) Few-shot learning with graph neural networks. arXiv:1711.04043. https:\/\/doi.org\/10.48550\/arXiv.1711.04043","DOI":"10.48550\/arXiv.1711.04043"},{"key":"11508_CR6","unstructured":"Tseng H, Lee H, Huang J, et\u00a0al (2020) Cross-domain few-shot classification via learned feature-wise transformation. In: 8th International conference on learning representations, ICLR"},{"key":"11508_CR7","doi-asserted-by":"publisher","unstructured":"Guo Y, Codella NC, Karlinsky L, et\u00a0al (2020) A broader study of cross-domain few-shot learning. In: European conference on computer vision. Springer, pp 124\u2013141. https:\/\/doi.org\/10.1007\/978-3-030-58583-9_8","DOI":"10.1007\/978-3-030-58583-9_8"},{"key":"11508_CR8","doi-asserted-by":"publisher","first-page":"4024","DOI":"10.1109\/TIP.2023.3293769","volume":"32","author":"J Zhang","year":"2023","unstructured":"Zhang J, Yang G, Hu P et al (2023) Semantic consistent embedding for domain adaptive zero-shot learning. IEEE Trans Image Process 32:4024\u20134035. https:\/\/doi.org\/10.1109\/TIP.2023.3293769","journal-title":"IEEE Trans Image Process"},{"issue":"109","key":"11508_CR9","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1016\/j.patcog.2023.109591","volume":"141","author":"F Lv","year":"2023","unstructured":"Lv F, Zhang J, Yang G et al (2023) Learning cross-domain semantic-visual relationships for transductive zero-shot learning. Pattern Recognit 141(109):591. https:\/\/doi.org\/10.1016\/j.patcog.2023.109591","journal-title":"Pattern Recognit"},{"key":"11508_CR10","doi-asserted-by":"publisher","unstructured":"Wang H, Deng Z (2021) Cross-domain few-shot classification via adversarial task augmentation. In: Zhou Z (ed), Proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI 2021, Virtual Event\/Montreal, Canada, 19-27 August 2021, pp 1075\u20131081. https:\/\/doi.org\/10.24963\/ijcai.2021\/149","DOI":"10.24963\/ijcai.2021\/149"},{"key":"11508_CR11","unstructured":"Adler T, Brandstetter J, Widrich M, et\u00a0al (2020) Cross-domain few-shot learning by representation fusion. arXiv:2010.06498"},{"key":"11508_CR12","doi-asserted-by":"publisher","unstructured":"Liang H, Zhang Q, Dai P, et\u00a0al (2021) Boosting the generalization capability in cross-domain few-shot learning via noise-enhanced supervised autoencoder. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9424\u20139434. https:\/\/doi.org\/10.1109\/iccv48922.2021.00929","DOI":"10.1109\/iccv48922.2021.00929"},{"key":"11508_CR13","doi-asserted-by":"crossref","unstructured":"Fu Y, Fu Y, Jiang YG (2021) Meta-FDMixup: cross-domain few-shot learning guided by labeled target data. In: Proceedings of the 29th ACM international conference on multimedia, pp 5326\u20135334","DOI":"10.1145\/3474085.3475655"},{"key":"11508_CR14","doi-asserted-by":"crossref","unstructured":"Zhang H, Cisse M, Dauphin YN, et\u00a0al (2017) mixup: beyond empirical risk minimization. arXiv:1710.09412","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"11508_CR15","unstructured":"Ravi S, Larochelle H (2017) Optimization as a model for few-shot learning. In: 5th international conference on learning representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings"},{"key":"11508_CR16","unstructured":"Rusu AA, Rao D, Sygnowski J, et\u00a0al (2018) Meta-learning with latent embedding optimization. arXiv:1807.05960"},{"key":"11508_CR17","doi-asserted-by":"crossref","unstructured":"Chen Z, Fu Y, Chen K, et\u00a0al (2019) Image block augmentation for one-shot learning. In: Proceedings of the AAAI conference on artificial intelligence, pp 3379\u20133386","DOI":"10.1609\/aaai.v33i01.33013379"},{"key":"11508_CR18","doi-asserted-by":"crossref","unstructured":"Wang YX, Girshick R, Hebert M, et\u00a0al (2018) Low-shot learning from imaginary data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7278\u20137286","DOI":"10.1109\/CVPR.2018.00760"},{"key":"11508_CR19","doi-asserted-by":"crossref","unstructured":"Li K, Zhang Y, Li K, et\u00a0al (2020) Adversarial feature hallucination networks for few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13,470\u201313,479","DOI":"10.1109\/CVPR42600.2020.01348"},{"key":"11508_CR20","doi-asserted-by":"crossref","unstructured":"Li W, Wang L, Xu J, et\u00a0al (2019) Revisiting local descriptor based image-to-class measure for few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7260\u20137268","DOI":"10.1109\/CVPR.2019.00743"},{"key":"11508_CR21","doi-asserted-by":"crossref","unstructured":"Zhu H, Koniusz P (2022) EASE: unsupervised discriminant subspace learning for transductive few-shot learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9078\u20139088","DOI":"10.1109\/CVPR52688.2022.00887"},{"key":"11508_CR22","doi-asserted-by":"publisher","unstructured":"Li H, Zhang L, Zhang D, et\u00a0al (2022) Transvlad: Focusing on locally aggregated descriptors for few-shot learning. In: European conference on computer vision, pp 524\u2013540. https:\/\/doi.org\/10.1007\/978-3-031-20044-1_30","DOI":"10.1007\/978-3-031-20044-1_30"},{"key":"11508_CR23","unstructured":"Chen WY, Liu YC, Kira Z, et\u00a0al (2019) A closer look at few-shot classification. arXiv:1904.04232"},{"issue":"4","key":"11508_CR24","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1109\/cvpr.2019.00503","volume":"41","author":"A Rozantsev","year":"2018","unstructured":"Rozantsev A, Salzmann M, Fua P (2018) Beyond sharing weights for deep domain adaptation. IEEE Trans Pattern Anal Mach Intell 41(4):801\u2013814. https:\/\/doi.org\/10.1109\/cvpr.2019.00503","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11508_CR25","doi-asserted-by":"publisher","unstructured":"Kang G, Jiang L, Yang Y, et\u00a0al (2019) Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4893\u20134902. https:\/\/doi.org\/10.1109\/cvpr.2019.00503","DOI":"10.1109\/cvpr.2019.00503"},{"key":"11508_CR26","doi-asserted-by":"publisher","unstructured":"Bousmalis K, Silberman N, Dohan D, et\u00a0al (2017) Unsupervised pixel-level domain adaptation with generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3722\u20133731. https:\/\/doi.org\/10.1109\/cvpr.2017.18","DOI":"10.1109\/cvpr.2017.18"},{"key":"11508_CR27","doi-asserted-by":"publisher","unstructured":"Ghifary M, Kleijn WB, Zhang M, et\u00a0al (2016) Deep reconstruction-classification networks for unsupervised domain adaptation. In: European conference on computer vision, Springer, pp 597\u2013613, https:\/\/doi.org\/10.1007\/978-3-319-46493-0_36","DOI":"10.1007\/978-3-319-46493-0_36"},{"key":"11508_CR28","doi-asserted-by":"publisher","unstructured":"Fernando B, Habrard A, Sebban M, et\u00a0al (2013) Unsupervised visual domain adaptation using subspace alignment. In: Proceedings of the IEEE international conference on computer vision, pp 2960\u20132967, https:\/\/doi.org\/10.1109\/iccv.2013.368","DOI":"10.1109\/iccv.2013.368"},{"key":"11508_CR29","unstructured":"Long M, Zhu H, Wang J, et\u00a0al (2016) Unsupervised domain adaptation with residual transfer networks. In: Advances in neural information processing systems, vol 29"},{"key":"11508_CR30","doi-asserted-by":"publisher","unstructured":"Tzeng E, Hoffman J, Saenko K, et\u00a0al (2017) Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7167\u20137176. https:\/\/doi.org\/10.1109\/cvpr.2017.316","DOI":"10.1109\/cvpr.2017.316"},{"key":"11508_CR31","unstructured":"Long M, Cao Z, Wang J, et\u00a0al (2018) Conditional adversarial domain adaptation. In: Advances in neural information processing systems, vol 31"},{"key":"11508_CR32","doi-asserted-by":"crossref","unstructured":"Fu Y, Xie Y, Fu Y, et\u00a0al (2022) Wave-SAN: wavelet based style augmentation network for cross-domain few-shot learning. CoRR arXiv:2203.07656","DOI":"10.1109\/CVPR52729.2023.02354"},{"key":"11508_CR33","doi-asserted-by":"publisher","unstructured":"Das R, Wang YX, Moura JM (2021) On the importance of distractors for few-shot classification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9030\u20139040. https:\/\/doi.org\/10.1109\/iccv48922.2021.00890","DOI":"10.1109\/iccv48922.2021.00890"},{"key":"11508_CR34","unstructured":"Liu X, Ji Z, Pang Y, et\u00a0al (2021) Self-taught cross-domain few-shot learning with weakly supervised object localization and task-decomposition. arXiv:2109.01302"},{"key":"11508_CR35","unstructured":"Yao F (2021) Cross-domain few-shot learning with unlabelled data. arXiv:2101.07899"},{"key":"11508_CR36","unstructured":"Requeima J, Gordon J, Bronskill J, et\u00a0al (2019) Fast and flexible multi-task classification using conditional neural adaptive processes. In: Advances in neural information processing systems 32: annual conference on neural information processing systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pp 7957\u20137968"},{"key":"11508_CR37","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, et\u00a0al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778. https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"11508_CR38","unstructured":"Wah C, Branson S, Welinder P, et\u00a0al (2011) The Caltech-UCSD Birds-200-2011 Dataset. Tech. Rep. CNS-TR-2011-001, California Institute of Technology"},{"key":"11508_CR39","doi-asserted-by":"publisher","unstructured":"Krause J, Stark M, Deng J, et\u00a0al (2013) 3d object representations for fine-grained categorization. In: Proceedings of the IEEE international conference on computer vision workshops, pp 554\u2013561. https:\/\/doi.org\/10.1109\/iccvw.2013.77","DOI":"10.1109\/iccvw.2013.77"},{"issue":"6","key":"11508_CR40","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/tpami.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou B, Lapedriza A, Khosla A et al (2017) Places: A 10 million image database for scene recognition. IEEE Trans Pattern Anal Mach Intell 40(6):1452\u20131464. https:\/\/doi.org\/10.1109\/tpami.2017.2723009","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11508_CR41","doi-asserted-by":"publisher","unstructured":"Van\u00a0Horn G, Mac\u00a0Aodha O, Song Y, et\u00a0al (2018) The inaturalist species classification and detection dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8769\u20138778. https:\/\/doi.org\/10.1109\/cvpr.2018.00914","DOI":"10.1109\/cvpr.2018.00914"},{"key":"11508_CR42","doi-asserted-by":"publisher","first-page":"7078","DOI":"10.1109\/tip.2022.3219237","volume":"31","author":"Y Fu","year":"2022","unstructured":"Fu Y, Fu Y, Chen J et al (2022) Generalized meta-FDMixup: cross-domain few-shot learning guided by labeled target data. IEEE Trans Image Process 31:7078\u20137090. https:\/\/doi.org\/10.1109\/tip.2022.3219237","journal-title":"IEEE Trans Image Process"},{"key":"11508_CR43","doi-asserted-by":"publisher","unstructured":"Sun J, Lapuschkin S, Samek W, et\u00a0al (2021) Explanation-guided training for cross-domain few-shot classification. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 7609\u20137616. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412941","DOI":"10.1109\/ICPR48806.2021.9412941"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11508-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11508-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11508-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T11:11:35Z","timestamp":1721041895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11508-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":43,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["11508"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11508-0","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"25 November 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"156"}}